File size: 10,209 Bytes
b334e29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
from collections import OrderedDict

import cv2
from cv2 import (CAP_PROP_FOURCC, CAP_PROP_FPS, CAP_PROP_FRAME_COUNT,
                 CAP_PROP_FRAME_HEIGHT, CAP_PROP_FRAME_WIDTH,
                 CAP_PROP_POS_FRAMES, VideoWriter_fourcc)

from annotator.uniformer.mmcv.utils import (check_file_exist, mkdir_or_exist, scandir,
                        track_progress)


class Cache:

    def __init__(self, capacity):
        self._cache = OrderedDict()
        self._capacity = int(capacity)
        if capacity <= 0:
            raise ValueError('capacity must be a positive integer')

    @property
    def capacity(self):
        return self._capacity

    @property
    def size(self):
        return len(self._cache)

    def put(self, key, val):
        if key in self._cache:
            return
        if len(self._cache) >= self.capacity:
            self._cache.popitem(last=False)
        self._cache[key] = val

    def get(self, key, default=None):
        val = self._cache[key] if key in self._cache else default
        return val


class VideoReader:
    """Video class with similar usage to a list object.

    This video warpper class provides convenient apis to access frames.
    There exists an issue of OpenCV's VideoCapture class that jumping to a
    certain frame may be inaccurate. It is fixed in this class by checking
    the position after jumping each time.
    Cache is used when decoding videos. So if the same frame is visited for
    the second time, there is no need to decode again if it is stored in the
    cache.

    :Example:

    >>> import annotator.uniformer.mmcv as mmcv
    >>> v = mmcv.VideoReader('sample.mp4')
    >>> len(v)  # get the total frame number with `len()`
    120
    >>> for img in v:  # v is iterable
    >>>     mmcv.imshow(img)
    >>> v[5]  # get the 6th frame
    """

    def __init__(self, filename, cache_capacity=10):
        # Check whether the video path is a url
        if not filename.startswith(('https://', 'http://')):
            check_file_exist(filename, 'Video file not found: ' + filename)
        self._vcap = cv2.VideoCapture(filename)
        assert cache_capacity > 0
        self._cache = Cache(cache_capacity)
        self._position = 0
        # get basic info
        self._width = int(self._vcap.get(CAP_PROP_FRAME_WIDTH))
        self._height = int(self._vcap.get(CAP_PROP_FRAME_HEIGHT))
        self._fps = self._vcap.get(CAP_PROP_FPS)
        self._frame_cnt = int(self._vcap.get(CAP_PROP_FRAME_COUNT))
        self._fourcc = self._vcap.get(CAP_PROP_FOURCC)

    @property
    def vcap(self):
        """:obj:`cv2.VideoCapture`: The raw VideoCapture object."""
        return self._vcap

    @property
    def opened(self):
        """bool: Indicate whether the video is opened."""
        return self._vcap.isOpened()

    @property
    def width(self):
        """int: Width of video frames."""
        return self._width

    @property
    def height(self):
        """int: Height of video frames."""
        return self._height

    @property
    def resolution(self):
        """tuple: Video resolution (width, height)."""
        return (self._width, self._height)

    @property
    def fps(self):
        """float: FPS of the video."""
        return self._fps

    @property
    def frame_cnt(self):
        """int: Total frames of the video."""
        return self._frame_cnt

    @property
    def fourcc(self):
        """str: "Four character code" of the video."""
        return self._fourcc

    @property
    def position(self):
        """int: Current cursor position, indicating frame decoded."""
        return self._position

    def _get_real_position(self):
        return int(round(self._vcap.get(CAP_PROP_POS_FRAMES)))

    def _set_real_position(self, frame_id):
        self._vcap.set(CAP_PROP_POS_FRAMES, frame_id)
        pos = self._get_real_position()
        for _ in range(frame_id - pos):
            self._vcap.read()
        self._position = frame_id

    def read(self):
        """Read the next frame.

        If the next frame have been decoded before and in the cache, then
        return it directly, otherwise decode, cache and return it.

        Returns:
            ndarray or None: Return the frame if successful, otherwise None.
        """
        # pos = self._position
        if self._cache:
            img = self._cache.get(self._position)
            if img is not None:
                ret = True
            else:
                if self._position != self._get_real_position():
                    self._set_real_position(self._position)
                ret, img = self._vcap.read()
                if ret:
                    self._cache.put(self._position, img)
        else:
            ret, img = self._vcap.read()
        if ret:
            self._position += 1
        return img

    def get_frame(self, frame_id):
        """Get frame by index.

        Args:
            frame_id (int): Index of the expected frame, 0-based.

        Returns:
            ndarray or None: Return the frame if successful, otherwise None.
        """
        if frame_id < 0 or frame_id >= self._frame_cnt:
            raise IndexError(
                f'"frame_id" must be between 0 and {self._frame_cnt - 1}')
        if frame_id == self._position:
            return self.read()
        if self._cache:
            img = self._cache.get(frame_id)
            if img is not None:
                self._position = frame_id + 1
                return img
        self._set_real_position(frame_id)
        ret, img = self._vcap.read()
        if ret:
            if self._cache:
                self._cache.put(self._position, img)
            self._position += 1
        return img

    def current_frame(self):
        """Get the current frame (frame that is just visited).

        Returns:
            ndarray or None: If the video is fresh, return None, otherwise
                return the frame.
        """
        if self._position == 0:
            return None
        return self._cache.get(self._position - 1)

    def cvt2frames(self,
                   frame_dir,
                   file_start=0,
                   filename_tmpl='{:06d}.jpg',
                   start=0,
                   max_num=0,
                   show_progress=True):
        """Convert a video to frame images.

        Args:
            frame_dir (str): Output directory to store all the frame images.
            file_start (int): Filenames will start from the specified number.
            filename_tmpl (str): Filename template with the index as the
                placeholder.
            start (int): The starting frame index.
            max_num (int): Maximum number of frames to be written.
            show_progress (bool): Whether to show a progress bar.
        """
        mkdir_or_exist(frame_dir)
        if max_num == 0:
            task_num = self.frame_cnt - start
        else:
            task_num = min(self.frame_cnt - start, max_num)
        if task_num <= 0:
            raise ValueError('start must be less than total frame number')
        if start > 0:
            self._set_real_position(start)

        def write_frame(file_idx):
            img = self.read()
            if img is None:
                return
            filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
            cv2.imwrite(filename, img)

        if show_progress:
            track_progress(write_frame, range(file_start,
                                              file_start + task_num))
        else:
            for i in range(task_num):
                write_frame(file_start + i)

    def __len__(self):
        return self.frame_cnt

    def __getitem__(self, index):
        if isinstance(index, slice):
            return [
                self.get_frame(i)
                for i in range(*index.indices(self.frame_cnt))
            ]
        # support negative indexing
        if index < 0:
            index += self.frame_cnt
            if index < 0:
                raise IndexError('index out of range')
        return self.get_frame(index)

    def __iter__(self):
        self._set_real_position(0)
        return self

    def __next__(self):
        img = self.read()
        if img is not None:
            return img
        else:
            raise StopIteration

    next = __next__

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self._vcap.release()


def frames2video(frame_dir,
                 video_file,
                 fps=30,
                 fourcc='XVID',
                 filename_tmpl='{:06d}.jpg',
                 start=0,
                 end=0,
                 show_progress=True):
    """Read the frame images from a directory and join them as a video.

    Args:
        frame_dir (str): The directory containing video frames.
        video_file (str): Output filename.
        fps (float): FPS of the output video.
        fourcc (str): Fourcc of the output video, this should be compatible
            with the output file type.
        filename_tmpl (str): Filename template with the index as the variable.
        start (int): Starting frame index.
        end (int): Ending frame index.
        show_progress (bool): Whether to show a progress bar.
    """
    if end == 0:
        ext = filename_tmpl.split('.')[-1]
        end = len([name for name in scandir(frame_dir, ext)])
    first_file = osp.join(frame_dir, filename_tmpl.format(start))
    check_file_exist(first_file, 'The start frame not found: ' + first_file)
    img = cv2.imread(first_file)
    height, width = img.shape[:2]
    resolution = (width, height)
    vwriter = cv2.VideoWriter(video_file, VideoWriter_fourcc(*fourcc), fps,
                              resolution)

    def write_frame(file_idx):
        filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
        img = cv2.imread(filename)
        vwriter.write(img)

    if show_progress:
        track_progress(write_frame, range(start, end))
    else:
        for i in range(start, end):
            write_frame(i)
    vwriter.release()